Single-agent advocacy variant of sophistry-bench for the Prime Intellect Reward Hacking Sprint. Pre-registered hypothesis: training Llama-3.2-1B on a programmatic claim-count cliff (peak at n=8) will cause cliff convergence within 100 GRPO steps; three adversarial canary rewards detect format-hacking. Self-contained (vendored from sophistry-bench v0.1.19) — no runtime dependency on the main package, to work around PI training-infra's exclude-newer index filter.
Project description
The author of this package has not provided a project description
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file sophistry_bench_sprint-0.1.5.tar.gz.
File metadata
- Download URL: sophistry_bench_sprint-0.1.5.tar.gz
- Upload date:
- Size: 498.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
640c59abf929fccc1b555aae634c3a8f170e46de04af1681e955697c221cd327
|
|
| MD5 |
27dfaca3037cda81051c8915695bdf3c
|
|
| BLAKE2b-256 |
70f677c2ca00d554fd4d39e11d01a3091d918ce2265af5464d05cb520b1e47d8
|
File details
Details for the file sophistry_bench_sprint-0.1.5-py3-none-any.whl.
File metadata
- Download URL: sophistry_bench_sprint-0.1.5-py3-none-any.whl
- Upload date:
- Size: 502.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bc2c29a3452aeee4e28a156926546922f16f3e58c2f63537ea253e99e0d75836
|
|
| MD5 |
71a6772ed3383d0afd2ad7b1537f80e4
|
|
| BLAKE2b-256 |
0ff729a0a1ce5f3af0d5e469357c55b1157f353342e8beb792ce249720c0237e
|
